AGENT SKILL

component-conformance-review

Checks every component in the AST-derived inventory against its spec in components.md, flagging undocumented variants, !important, inline style= and unwrapped primitives. Use when a design-test run has finished token-conformance-review.

License 许可
MIT
所属仓库
Eliyce/paqad-ai
最近更新
2026-11-13
Stars
★ 8
Forks
0

01 前言 Front Matter

name
component-conformance-review
metadata
{ "cacheable": "false", "model_tier": "reasoning", "paqad-meta": "skill.meta.yaml", "output_format": "markdown" }
description
Checks every component in the AST-derived inventory against its spec in components.md, flagging undocumented variants, !important, inline style= and unwrapped primitives. Use when a design-test run has finished token-conformance-review.

02 资源文件 8

03 SKILL.md 正文

What It Does

Audits the project's UI components against components.md. The AST-derived component inventory is the subject; the contract is the standard. Every component used in source must appear in components.md with declared variants, states, and permitted compositions. Override sprawl (!important, inline style=, undocumented Tailwind combinations, shadcn primitives wrapped without spec) is a finding.

Use This When

For every design-test run, after token-conformance-review. The two together form the "is the contract followed at the source level" pair.

Inputs

  • Read docs/instructions/design-system/components.md.
  • Read the contract-summary from design-system-coverage (declared component clauses).
  • Read references/component-conformance-checklist.md before scanning.

Procedure

The set difference between source and contract is deterministic, drive it with the scripts. Reserve LLM judgment for severity and the "is this primitive correctly wrapped" question.

  1. Run scripts/derive-inventory.sh [components-dir] → <name>\t<source-file> TSV. The script already excludes tests, stories, type decls, barrels, and lower-case helpers.
  2. Run scripts/parse-components-md.sh <components.md> → <name>\t<variants-csv>\t<states-csv> TSV. Empty CSV slots are -.
  3. Run scripts/diff-inventories.sh --source <derived> --declared <parsed>. Each row is a deterministic gap:
    • in-source-not-declared\tName\t<file> → documentation-drift finding, medium.
    • declared-not-in-source\tName\t- → documentation-drift finding (contract references a non-existent component), medium to high depending on whether the contract is what the team intends to build.
  4. Run runtime/scripts/design/scan-overrides.sh to enumerate !important, inline style=, arbitrary Tailwind brackets, undocumented utility combos. The LLM decides whether each hit is a missing prop on a declared component or genuine code smell.
  5. For each declared component, verify its declared variants are implemented in the source file. Missing variant → component finding, high.

Output Contract

  • Match assets/output.template.md. contract_ref is components.md → <ComponentName> or patterns.md → override budget.
  • Default severity high for missing-variant findings, medium for override sprawl, low for cosmetic deviations.
  • Output must pass scripts/lint-findings.sh (exit 0).

Escalate / Stop Conditions

  • Ask when components.md has no entries: defer to design-system-coverage (tier likely bare).
  • Warn when the inventory exceeds 100 components: the audit may need to be chunked.

Resources

  • references/component-conformance-checklist.md
  • scripts/derive-inventory.sh: AST-ish inventory of src/components/**.
  • scripts/parse-components-md.sh: declared inventory + variants/states from components.md.
  • scripts/diff-inventories.sh: set difference between source and declared.
  • scripts/lint-findings.sh
  • assets/output.template.md
  • agents/openai.yaml

04 同仓库更多 Skills

Eliyce
Eliyce/paqad-ai

sample-skill

Sample bundled skill fixture

★ 8
Eliyce
Eliyce/paqad-ai

processing-invoices

Turns a supplier invoice into one ledger line. Use when a supplier invoice arrives and needs booking.

★ 8
Eliyce
Eliyce/paqad-ai

processing-invoices

Turns a supplier invoice into one ledger line. Use when a supplier invoice arrives and needs booking.

★ 8
Eliyce
Eliyce/paqad-ai

understand-idea

Chat and Claude Code: Step 1 of the discover journey: clarifies the goal, who benefits, success and constraints into the idea block. Use when the journey directs it to step 1, not directly.

★ 8
Eliyce
Eliyce/paqad-ai

size-work

Chat and Claude Code: Suggest a size for a ticket from comparable finished work, as a labelled suggestion the team still owns. Use it when someone asks "how big is this?", "roughly how much work is ABC-12?", or wants a backlog item sized. It finds the team's sizing scale at first use, picks two to five of the closest finished tickets with links, and gives a size or range with the drivers behind it and a confidence of low, medium or high, lowered and explained when the area's documents are template text. Every result is labelled a suggested size, never a date or a commitment. It writes nothing into the size field unless the user says "set it", and it refuses to overwrite an existing size unless the user asks to replace it. Produces the sizing block of the record.

★ 8
Eliyce
Eliyce/paqad-ai

refine-ticket

Chat and Claude Code: Improve one or more existing tracker tickets without losing the author's intent. Use it when someone wants a ticket read, diagnosed and tidied up ("this ticket is vague", "fix up ABC-12", "split this, it's too big"). It reads each ticket in full and snapshots it with its last-updated time, says what is wrong with evidence, and proposes a field-by-field before and after change set limited to summary, description, labels, parent, links and new child tickets on a split. It writes nothing until an explicit "apply it" bound to that exact change set, re-checks the ticket for conflicting edits just before writing, never replaces rich descriptions with plain text, never deletes or closes a ticket, and reads each ticket back after applying. Produces the existing and changes blocks of the record.

★ 8